© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23100
    Prev
    Next
    INDEX
    Explanations

    sentences that convey an official position or statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    505
    +0.13
    0.8%
    165
    +0.12
    0.8%
    321
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.13
    0.12
    165
    +0.12
    0.12
    189
    +0.12
    0.12
    Negative Logits
     repeated
    -1.63
     [$\
    -1.61
    [$
    -1.60
     finally
    -1.58
     [$
    -1.56
     flag
    -1.56
     brow
    -1.52
     clustered
    -1.48
    >$
    -1.38
     row
    -1.35
    POSITIVE LOGITS
    lists
    1.90
    .
    1.78
    /
    1.75
    istry
    1.67
     että
    1.67
    nah
    1.66
    icles
    1.66
    alta
    1.59
     Ideas
    1.59
     arsenal
    1.58
    Activations Density 1.286%

    No Known Activations